AI revolutionizes search for new antimicrobial molecules

César de la Fuente, a bioengineer, and his interdisciplinary lab are leveraging AI tools like Codex and ChatGPT to identify potential antimicrobial molecules from the genomes of both living and extinct organisms. Drug-resistant microbes are a growing global threat, with five million deaths recorded in 2021 due to bacterial antimicrobial resistance, a figure expected to double by 2050. De la Fuente emphasizes that the lack of new antibiotic classes in 50 years highlights the urgency of this work. The lab uses deep-learning models to analyze biological sequences, significantly reducing the time required to identify candidate molecules. AI helps bridge gaps between disciplines, enabling biologists and programmers to collaborate effectively. De la Fuente notes that while AI is crucial for hypothesis generation and data analysis, ground-truth experiments remain essential to validate predictions. He views AI as a tool to expand scientific understanding, akin to historical advancements like the telescope and microscope, which transformed our view of the world.